arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.03090cs.LGcs.AI
收藏

RISAN:健壮的实例特定弃权网络

RISAN: Robust Instance Specific Abstention Network

International Institute of Technology Hyderabad(海得拉巴国际信息技术学院);Microsoft Research(微软研究院)

Bhavya Kalra, Kulin Shah, Naresh Manwani

摘要:

在本文中,我们提出了用于学习特定于实例的弃权(拒绝选项)二进制分类器的深度架构。所提出的方法使用Kulin Shah和Naresh Manwani在(“Online主动学习of Optional Classifiers”,AAAI,2020)中描述的双S形损失函数作为性能度量。我们表明,双S形损失的分类校准。我们还证明了0-d-1损失的超额风险的上界是双S形损失的超额风险。我们推导出的泛化误差界的建议架构拒绝选项分类。为了证明所提出的方法的有效性,我们用几个真实世界的数据集进行了实验。我们观察到,所提出的方法不仅表现出与最先进的方法相当,它对标签噪声也是鲁棒的。我们还提供了可视化来观察网络学习到的与弃权决策相对应的重要特征。

英文摘要:

In this paper, we propose deep architectures for learning instance specific abstain (reject option) binary classifiers. The proposed approach uses double sigmoid loss function as described by Kulin Shah and Naresh Manwani in ("Online Active Learning of Reject Option Classifiers", AAAI, 2020), as a performance measure. We show that the double sigmoid loss is classification calibrated. We also show that the excess risk of 0-d-1 loss is upper bounded by the excess risk of double sigmoid loss. We derive the generalization error bounds for the proposed architecture for reject option classifiers. To show the effectiveness of the proposed approach, we experiment with several real world datasets. We observe that the proposed approach not only performs comparable to the state-of-the-art approaches, it is also robust against label noise. We also provide visualizations to observe the important features learned by the network corresponding to the abstaining decision.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑